Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1929 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.3563. Min Act: -0.1700
Data Index: 2789420 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2622. Min Act: -0.1700
Data Index: 5251863 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2936. Min Act: -0.1700
Data Index: 4600414 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2936. Min Act: -0.1700
Data Index: 4171179 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2936. Min Act: -0.1700
Data Index: 328107 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2936. Min Act: -0.1700
Data Index: 3671982 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2622. Min Act: -0.1700
Data Index: 3660289 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2936. Min Act: -0.1700
Data Index: 35503 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2936. Min Act: -0.1700
Data Index: 8365100 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2936. Min Act: -0.1700
Data Index: 5558766 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2936. Min Act: -0.1700
Data Index: 5455981 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2936. Min Act: -0.1700
Data Index: 2821623 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2936. Min Act: -0.1700
Data Index: 5069053 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2622. Min Act: -0.1700
Data Index: 3356280 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2622. Min Act: -0.1700
Data Index: 42821 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2622. Min Act: -0.1700
Data Index: 3607283 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2622. Min Act: -0.1700
Data Index: 4009783 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2622. Min Act: -0.1700
Data Index: 4202547 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2622. Min Act: -0.1700
Data Index: 667735 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3563. Min Range: -3.3563
Max Act: 3.2622. Min Act: -0.1700
Data Index: 4496782 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19